Trading
Strategies, brokerages and prediction markets. As of 2026-11-21, 495 indexed products match this subcategory (66 with full profiles); 280 were published in the last 90 days, against 124 in the 90 days before, slower than the catalogue as a whole. By GitHub stars, FinceptTerminal leads, holding 35% of the stars of the 319 products here with their own repository. The most common form is MCP servers (99% of indexed products).
SubcategorySegment label: Lagging the catalogue DER
Segment statistics
Whole catalogue (all 495 indexed products, not only profiled ones). Calculated 2026-11-21.
Lagging the catalogue. Mid-sized for its level, with launches growing more slowly than the catalogue’s. Size is ranked against the other subcategory nodes; momentum compares this node’s launches in the last 90 days with the 90 before, relative to the whole catalogue’s ratio (score 62 or more = faster, 38 or less = slower; below 5 dated launches it is not measured and the label uses size alone).
Concentration. The Herfindahl–Hirschman index (HHI) adds up each project’s squared share of stars. At 0.203, attention is spread as if across about 5 equally popular projects. Using the common competition-policy thresholds (0.15 and 0.25), that is moderately concentrated. Stars measure attention, not usage or quality.
Which product forms serve it
The same need is met by MCP servers, agent skills, plugins, extensions and frameworks. This counts each form across the whole catalogue.
| Product type | Indexed | Share | With a profile |
|---|---|---|---|
| MCP servers | 488 | 98.6% | 59 |
| Agent skills | 5 | 1.0% | 5 |
| Agent projects | 2 | 0.40% | 2 |
3 capabilities
Indexed = whole catalogue; profiled = products with their own page. A product can sit in several, so the rows do not add up to the total.
| Capability | Indexed | Profiled | New, 90 days | Label |
|---|---|---|---|---|
| Prediction MarketsOdds and markets on future events. | 240 | 16 | 144 | Crowded |
| Brokerage IntegrationConnecting to brokerage accounts and portfolios. | 134 | 20 | 80 | Lagging the catalogue |
| Algorithmic TradingDesigning and backtesting trading strategies. | 117 | 34 | 52 | Lagging the catalogue |
Top 40 products by GitHub stars
Search the directoryProfiled products only (66 of 495), ranked by the stars of their own repository. Products that live in a subfolder of a larger repository (common for skills) show that whole repository's stars and are ranked after them; products without a repository come last. Stars are popularity, not quality or installs.
| # | Product | Type | Publisher | Capabilities | GitHub stars | Last push | Licence | Save and compare |
|---|---|---|---|---|---|---|---|---|
| 1 | FinceptTerminalFinceptTerminal is a modern finance application offering advanced market analytics, investment research, and economic data tools, designed for interactive exploration and data-driven decision-making in a user-friendly environment. | Agent project | Fincept-Corporation | 34k | 2d ago | AGPL-3.0 | ||
| 2 | hummingbotOpen source software that helps you create and deploy high-frequency crypto trading bots | Agent project | hummingbot | 21k | 1d ago | Apache-2.0 | ||
| 3 | QuantDingerThe most complete open-source, self-hosted Agentic Trading OS—AI research, Python strategies, factor discovery, backtesting, optimization, paper/live multi-asset execution, risk controls, monitoring, MCP, and multi-tenant SaaS in one auditable stack. | MCP server | OpenByteInc | 14k | today | Apache-2.0 | ||
| 4 | day-trader-skill11 Claude skills for day trading: scan thousands of charts, track breaking news, time every entry and exit, and replay every outcome before you risk a dollar. | Agent skill | Jakeschincariol | 9.0k | 1mo ago | MIT | ||
| 5 | Finance Toolkit500+ transparent financial methods calculated from raw statements, not third-party endpoints. | MCP server | JerBouma | 5.5k | today | MIT | ||
| 6 | ai-traderBacktrader-powered backtesting framework for algorithmic trading, featuring 20+ strategies, multi-market support, CLI tools, and an integrated MCP server for professional traders. | MCP server | whchien | 1.1k | 7mo ago | GPL-3.0 | ||
| 7 | alpaca-mcp-serverAlpaca’s official MCP Server lets you trade stocks, ETFs, crypto, and options, run data analysis, and build strategies in plain English directly from your favorite LLM tools and IDEs | MCP server | alpacahq | 1.1k | 8d ago | MIT | ||
| 8 | world-intel-mcp160-tool MCP server for real-time global intelligence from free public APIs: markets, liquidity, prediction markets, SEC filings, conflict, military, aircraft-cohort early warning, migration and border flows, cyber, climate, news and more. Dated observation history, 29 research prompts, cited briefs, geofences, SSE dashboard. MIT, no paid API keys. | MCP server | marc-shade | 1.1k | 1mo ago | MIT | ||
| 9 | CNEquityOpen-source China A-share data lake for AI agents: prices, fundamentals, flows, events, PIT. | MCP server | rootSunc | 1.1k | 8d ago | Apache-2.0 | ||
| 10 | awesome-trading-agentsCurated list of LLM-driven trading agents, MCP servers, and agent skills for market research, strategy, and execution. | MCP server | LLMQuant | 1.0k | 3mo ago | CC0-1.0 | ||
| 11 | digital-oracleAI agent skill that answers macro questions — housing, gold, BTC, geopolitics — with probability estimates mined from 13 financial data sources (Polymarket, Kalshi, CFTC, SEC & more). For Claude Code / Cursor / Codex / OpenClaw. | 让 AI Agent 从金融数据中挖掘宏观趋势的数字先知 | Agent skill | komako-workshop | 915 | 3mo ago | MIT | ||
| 12 | kraken-cliTrade crypto, tokenized stocks, forex and futures on Kraken from your terminal or your AI agent. Built-in MCP server for Claude, Codex and Cursor, JSON output, and paper trading on live prices. | MCP server | krakenfx | 813 | 23d ago | MIT | ||
| 13 | maverick-mcpStock market MCP server for Yahoo Finance data, technical analysis, portfolio tracking, and Python backtesting. Runs locally with no API key for core tools. | MCP server | wshobson | 733 | 8d ago | MIT | ||
| 14 | hypergrok-trading-deskHyperliquid trading desk for AI agents: 7 roles, 17 skills and keyless market tools. Research first; execution requires your API wallet and approved tickets. Grok Bot, Claude Code, Cursor, Codex, Gemini CLI and Grok Build. | Agent skill | galleonlabs | 578 | 4d ago | MIT | ||
| 15 | Oracle3 prediction-market agent toolsKalshi and Polymarket data, venue fees, no-arbitrage checks and paper execution for AI agents. | MCP server | YichengYang-Ethan | 569 | 5d ago | Apache-2.0 | ||
| 16 | tossinvest-cli공식 API에 없는 30+ 기능까지, 터미널과 AI에서 쓰세요. 토스증권 비공식 CLI·MCP. | MCP server | JungHoonGhae | 523 | 5d ago | MIT | ||
| 17 | Polymarket Paper TraderPolymarket paper trading for AI agents: $10k paper money, real order books, official fees. | MCP server | agent-next | 509 | 20d ago | MIT | ||
| 18 | finlab-aiQuantitative trading toolkit with 900+ data columns, backtesting, and 60+ strategy examples. | MCP server | koreal6803 | 427 | 4d ago | — | ||
| 19 | blockrun-mcpWeb search, deep research, prediction markets & crypto data for AI agents. Pay per call via x402. | MCP server | BlockRunAI | 390 | 3d ago | MIT | ||
| 20 | Risk-Aware Trading AgentsAI trading agents for US stocks: point-in-time news backtests, a frozen 2026 market, paper trading | MCP server | jackson-cmd | 356 | 1d ago | MIT | ||
| 21 | qanatA data platform for investment research. Ingests financial data sources and computes point-in-time financial metrics for valuation and screening. Delivered as an MCP server. | MCP server | fidetolabs | 334 | 7d ago | MIT | ||
| 22 | interactive-brokers-mcpInteractive Brokers MCP Server | MCP server | code-rabi | 227 | 4mo ago | MIT | ||
| 23 | polymarket-toolkitRead-only Polymarket data tools for AI agents: profiles, PnL, market scans. No keys, no orders. | MCP server | runesleo | 204 | 3d ago | MIT | ||
| 24 | CrawlHiveMemecoin safety scanner for Solana, BNB and Robinhood Chain with an onchain track record | MCP server | crawlhive.xyz | 155 | 28d ago | MIT | ||
| 25 | openInvestInvestment runtime for AI agents — LLM investment committee, portfolio ledger, decision accounting | MCP server | longsizhuo | 142 | 8d ago | MIT | ||
| 26 | cre-agent-skillsCommercial real estate AI agent skills for CRE underwriting, due diligence, financing, brokerage, legal and closing workflows - standalone prompts for Claude Code, ChatGPT, Cursor, and other LLMs. | Agent skill | ahacker-1 | 142 | 2mo ago | Apache-2.0 | ||
| 27 | AI Trading SignalsLive crypto trading signals for AI agents: entry, stop, target, reasoning and verified outcomes. | MCP server | roman-rr | 130 | 4d ago | — | ||
| 28 | Trade ItConnect brokerage accounts to AI assistants: holdings, orders, asset lookup, and approved trading. | MCP server | tradeit.app | 62 | 1d ago | CC0-1.0 | ||
| 29 | SimmerTrade prediction markets with AI agents — skill discovery, autoresearch, and execution. | MCP server | adlai88 | 56 | 1d ago | MIT | ||
| 30 | MT5-QuantMT5 strategy development with 87 tools. Backtest, optimize, debug MQL5 EAs on macOS/Linux. | MCP server | masdevid | 54 | 3d ago | MIT | ||
| 31 | skforecast-aiForecast time series in CSV files: deterministic skforecast workflows and the script that ran. | MCP server | skforecast | 52 | 9d ago | Apache-2.0 | ||
| 32 | TRARead-only gates of autonomous trading agents with deterministic execution: cost, data, validation. | MCP server | BijectiveLabs | 47 | 3d ago | MIT | ||
| 33 | trading-research-agentsRead-only gates of autonomous trading agents with deterministic execution: cost, data, validation. | MCP server | BijectiveLabs | 47 | 3d ago | MIT | ||
| 34 | Robinhood Portfolio ResearchRead-only research tools for Robinhood portfolio data | MCP server | verygoodplugins | 41 | 3mo ago | MIT | ||
| 35 | sports-hub42 sports API providers, 410 tools: scores, stats, odds, esports, chess, motorsport & more. | MCP server | lacausecrypto | 41 | 1mo ago | MIT | ||
| 36 | trayd-mcpTrade Robinhood through natural language in Claude Code. | MCP server | teamtrayd | 41 | 4mo ago | — | ||
| 37 | sportsdata-mcpLive sports data and cross-book betting odds — 801 tools, 63 providers, 43 needing no key. | MCP server | DanielTomaro13 | 37 | 6d ago | MIT | ||
| 38 | DeFi Trading AgentsDeFi agent definitions JSON API - crypto trading portfolio management bots | MCP server | nirholas | 37 | 10d ago | — | ||
| 39 | StratEvoQuantitative trading: quotes, backtesting, screening, and genetic algorithm strategy evolution. | MCP server | NeuZhou | 34 | 7mo ago | — | ||
| 40 | mcp-server-kalshiMCP server for end-to-end trading on Kalshi prediction markets: discover, research, trade. | MCP server | 9crusher | 32 | 2mo ago | MIT |
Most common integrations
Third-party services named by products in this node, whole catalogue.
| Integration | Products | Share |
|---|---|---|
| Solana | 17 | 3.4% |
| X (Twitter) | 2 | 0.4% |
| GitHub | 1 | 0.2% |
| Google Workspace | 1 | 0.2% |
| GraphQL | 1 | 0.2% |
| 1 | 0.2% | |
| Stripe | 1 | 0.2% |
| Telegram | 1 | 0.2% |
| YouTube | 1 | 0.2% |
Launches per month
New Trading products per monthSRC
Whole catalogue, by publication month, 2025-06 to 2026-11. The last month is partial; undated products are excluded.
Show the data as a table
| Products published (products) | |
|---|---|
| 2025-06 | 1 |
| 2025-08 | 2 |
| 2025-11 | 1 |
| 2025-12 | 3 |
| 2026-01 | 6 |
| 2026-02 | 11 |
| 2026-03 | 19 |
| 2026-04 | 27 |
| 2026-05 | 19 |
| 2026-06 | 29 |
| 2026-07 | 61 |
| 2026-08 | 41 |
| 2026-09 | 68 |
| 2026-10 | 111 |
| 2026-11 | 92 |
Related opportunities
Opportunity radarScored gaps for this node or anything beneath it. Scores rank hypotheses; they do not predict demand.
No scored opportunity here
Capability gaps are only scored inside subcategories with at least 20 indexed products, and only the top 80 are kept. None falls under this node.
Limits of these numbers
- Products are placed here by whole-word keyword rules on their name, description and repository topics, and inherit every ancestor of a matched node. Products that do this without naming it are missed; ambiguous words cause false matches. Methodology
- About half of the catalogue matches no node at all, so absolute counts understate every category.
- Launch counts use the publication date each source reports; for auto-discovered repositories that is the repository’s creation date.
- Stars and concentration cover only products with their own repository (not a subfolder of a larger one). They measure attention, not adoption.
Page data last updated .